ChartDialogs: Plotting from Natural Language Instructions
By Yutong Shao, Ndapandula Nakashole. 2020
13 citations recorded by the source corpus.
This paper presents the problem of conversational plotting agents that carry out plotting actions from natural language instructions. To facilitate the development of such agents, we introduce ChartDialogs, a new multi-turn dialog dataset, covering a popular plotting library, matplotlib. The dataset contains over 15,000 dialog turns from 3,200 dialogs covering the majority of matplotlib plot types. Extensive experiments show the best-performing method achieving 61% plotting accuracy, demonstrating that the dataset presents a non-trivial challenge for future research on this task.
Subfields: Artificial Intelligence, Natural Language Generation, Human-Computer Interaction
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Chitta Baral
- Swaroop Mishra
- Hannaneh Hajishirzi
- Daniel Khashabi
- Tom Young
- Erik Cambria
- Percy Liang
- Luke S. Zettlemoyer
In Human-Computer Interaction
Citations in the corpus
- Cross-Task Generalization via Natural Language Crowdsourcing Instructions (2021, neutral): “, 2020), programming instructions (Lin et al., 2018; Shao and Nakashole, 2020), inter alia.”
- Natural Instructions: Benchmarking Generalization to New Tasks from Natural Language Instructions (2021, background): “, 2020), visualizations (Shao and Nakashole, 2020), console commands (Lin et al.”
- Recent advances in deep learning based dialogue systems: a systematic survey (2021, background): “Conversational Plotting Shao and Nakashole (2020) CONAN A multilingual dataset for hatespeech tackling.”